Skip to content

Benchmark

MTEB(fas, v2) - STS

Embedding benchmarks measure how well models find related items, for example when matching a search to relevant results. Scores are percentages.

Models measured
12
Scores recorded
12
Sources
1
IQ weight
0.71

Score distribution

79.5%
Mean
80%
Median
3.6%
Std dev
76.8%
10th percentile
82.8%
90th percentile
69.1%
Min
69.1%83.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.71 for embedding models, measured over 12 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard